Clinical Use of a Commercial Artificial Intelligence-Based Software for Autocontouring in Radiation Therapy: Geometric Performance and Dosimetric Impact.

PURPOSE: When autocontouring based on artificial intelligence (AI) is used in the radiotherapy (RT) workflow, the contours are reviewed and eventually adjusted by a radiation oncologist before an RT treatment plan is generated, with the purpose of improving dosimetry and reducing both interobserver variability and time for contouring. The purpose of this study was to evaluate the results of application of a commercial AI-based autocontouring for RT, assessing both geometric accuracies and the influence on optimized dose from automatically generated contours after review by human operator. MATERIALS AND METHODS: A commercial autocontouring system was applied to a retrospective database of 40 patients, of which 20 were treated with radiotherapy for prostate cancer (PCa) and 20 for head and neck cancer (HNC). Contours resulting from AI were compared against AI contours reviewed by human operator and human-only contours using Dice similarity coefficient (DSC), Hausdorff distance (HD), and relative volume difference (RVD). Dosimetric indices such as Dmean, D0.03cc, and normalized plan quality metrics were used to compare dose distributions from RT plans generated from structure sets contoured by humans assisted by AI against plans from manual contours. The reduction in contouring time obtained by using automated tools was also assessed. A Wilcoxon rank sum test was computed to assess the significance of differences. Interobserver variability of the comparison of manual vs. AI-assisted contours was also assessed among two radiation oncologists for PCa. RESULTS: For PCa, AI-assisted segmentation showed good agreement with expert radiation oncologist structures with average DSC among patients ≥ 0.7 for all structures, and minimal radiation oncology adjustment of structures (DSC of adjusted versus AI structures ≥ 0.91). For HNC, results of comparison between manual and AI contouring varied considerably e.g., 0.77 for oral cavity and 0.11-0.13 for brachial plexus, but again, adjustment was generally minimal (DSC of adjusted against AI contours 0.97 for oral cavity, 0.92-0.93 for brachial plexus). The difference in dose for the target and organs at risk were not statistically significant between human and AI-assisted, with the only exceptions of D0.03cc to the anal canal and Dmean to the brachial plexus. The observed average differences in plan quality for PCa and HNC cases were 8% and 6.7%, respectively. The dose parameter changes due to interobserver variability in PCa were small, with the exception of the anal canal, where large dose variations were observed. The reduction in time required for contouring was 72% for PCa and 84% for HNC. CONCLUSIONS: When an autocontouring system is used in combination with human review, the time of the RT workflow is significantly reduced without affecting dose distribution and plan quality.

Moderately hypofractionated salvage radiotherapy in patients with biochemical recurrence of prostate cancer after prostatectomy: long-term results and comparative analysis of two schedules.

Hypofractionation in salvage radiotherapy (HSRT) for biochemical recurrence of prostatic cancer after prostatectomy is a debated issue and at present, it should be considered purely investigational because of the lack of evidence supporting its use. In this study, we report the outcomes of patients presenting with biochemical recurrence after radical prostatectomy who received HSRT. The additional aim of this study is to compare two moderately HSRT schedules. Patients treated to prostate bed with daily Image Guided-VMAT and a total dose of 65 Gy/26 fractions (Group A) or 66 Gy/30 fractions (Group B) were included in the study. Inclusion criteria were: pN0/pNx, pre-HSRT PSA ≥0.2 ng/ml and ≤1 ng/ml, no evidence of pelvic/extrapelvic disease at restaging, no pelvic irradiation or dose boost on macroscopic local recurrence, no neoadjuvant/concomitant Androgen Deprivation Therapy (ADT), follow-up ≥36 months, and available pre/post HSRT data. Genitourinary (GU) and gastrointestinal (GI) toxicities, early and late, were assessed using CTCAE Vers. 5.0. One hundred patients were retrospectively identified to 50 in each group. Median follow-up was 59 months. All patients completed the prescribed HSRT. 5-year biochemical failure-free survival, local control, distant relapse-free survival, and ADT- free survival were 52.1%, 85.9%, 63.7%, and 73.2%, respectively. No significant differences in these outcomes were found between the two groups. On multivariate analysis, a hypofractionation schedule was not associated with any outcome, but ISUP score ≥ 4 and pre-HSRT PSA were associated with worse biochemical failure-free survival while only ISUP score ≥ 4 was associated with worse distant relapse-free survival. No Grade 3 GU/GI acute event was reported; 6 (6%) and 2 (2%) patients experienced late Grade ≥ 2 GU and GI events, respectively. No difference was found between the two groups neither in acute nor in late GU/GI toxicities. Our findings demonstrate that HSRT is feasible, effective, and safe. Our analysis did not show any significant difference between the two hypofractionated schedules. Further studies and randomized controlled trials are required in order to confirm these results and to identify the optimal hypofractionated schedule in the salvage setting.

Predicting Local Failure after Partial Prostate Re-Irradiation Using a Dosiomic-Based Machine Learning Model.

The aim of this study is to predict local failure after partial prostate re-irradiation for the treatment of isolated locally recurrent prostate cancer by using a machine learning classifier based on radiomic features from pre-treatment computed tomography (CT), positron-emission tomography (PET) and biological effective dose distribution (BED) of the radiotherapy plan. The analysis was conducted on a monocentric dataset of 43 patients with evidence of isolated intraprostatic recurrence of prostate cancer after primary external beam radiotherapy. All patients received partial prostate re-irradiation delivered by volumetric modulated arc therapy. The gross tumor volume (GTV) of each patient was manually contoured from planning CT, choline-PET and dose maps. An ensemble machine learning pipeline including unbalanced data correction and feature selection was trained using the radiomic and dosiomic features as input for predicting occurrence of local failure. The model performance was assessed using sensitivity, specificity, accuracy and area under receiver operating characteristic curves of the score function in 10-fold cross validation repeated 100 times. Local failure was observed in 13 patients (30%), with a median time to recurrence of 36.7 months (range = 6.1-102.4 months). A four variables ensemble machine learning model resulted in accuracy of 0.62 and AUC 0.65. According to our results, a dosiomic machine learning classifier can predict local failure after partial prostate re-irradiation.

Prognostic Nutritional Index Predicts Toxicity in Head and Neck Cancer Patients Treated with Definitive Radiotherapy in Association with Chemotherapy.

BACKGROUND: The Prognostic Nutritional Index (PNI) is a parameter of nutritional and inflammation status related to toxicity in cancer treatment. Since data for head and neck cancer are scanty, this study aims to investigate the association between PNI and acute and late toxicity for this malignancy. METHODS: A retrospective cohort of 179 head and neck cancer patients treated with definitive radiotherapy with induction/concurrent chemotherapy was followed-up (median follow-up: 38 months) for toxicity and vital status between 2010 and 2017. PNI was calculated according to Onodera formula and low/high PNI levels were defined according to median value. Odds ratio (OR) for acute toxicity were calculated through logistic regression model; hazard ratios (HR) for late toxicity and survival were calculated through the Cox proportional hazards model. RESULTS: median PNI was 50.0 (interquartile range: 45.5-53.5). Low PNI was associated with higher risk of weight loss > 10% during treatment (OR = 4.84, 95% CI: 1.73-13.53 for PNI < 50 versus PNI ≥ 50), which was in turn significantly associated with worse overall survival, and higher risk of late mucositis (HR = 1.84; 95% CI:1.09-3.12). PNI predicts acute weight loss >10% and late mucositis. CONCLUSIONS: PNI could help clinicians to identify patients undergoing radiotherapy who are at high risk of acute and late toxicity.

Partial prostate re-irradiation for the treatment of isolated local recurrence of prostate cancer in patients previously treated with primary external beam radiotherapy: short-term results of a monocentric study.

Many different therapeutic options are available for locally recurrent prostate cancer (PCa). However, standard treatment has not yet been established. We conducted a partial prostate re-irradiation (PPR) program for the treatment of isolated and limited-size intraprostatic recurrences, in patients who previously underwent external beam radiation therapy (EBRT) as primary treatment for prostatic cancer (PCa). The analysis of this experience in terms of feasibility, toxicity, and efficacy is reported. The inclusion criteria of this retrospective analysis were: previous definitive EBRT, evidence of biochemical recurrence, radiological detection of isolated local relapse, and PPR as local salvage therapy. Gastrointestinal (GI) and genitourinary (GU) toxicities were registered according to the RTOG/EORTC criteria. Between July 2012 and May 2019, 44 patients were treated with PPR. All patients completed the planned treatment. The median follow-up was 25.4 months. Tumor progression was observed in 18 patients (40.9%). Two-year local control, biochemical failure-, and clinical relapse-free survival rates were 90.1%, 58.3%, and 67.9%, respectively. The occurrence of biochemical failure after PPR is lower for patients with the time interval between the primary EBRT and first biochemical failure >4 years; local control results strongly associated with a biologically effective dose (BED) at first EBRT >177 Gy. No acute grade 3 or greater toxic events were observed. Two late grade 3 GU toxicities were reported. Although retrospective in design, our study indicates that PPR appears as a feasible, well-tolerated, and effective salvage treatment for isolated local PCa recurrence. Long term data are required in order to confirm these results.

Electron radiotherapy (IOERT) for applications outside of the breast: Dosimetry and influence of tissue inhomogeneities.

PURPOSE: The purpose of study is to investigate the dosimetry of electron intraoperative radiotherapy (IOERT) of the Intraop Mobetron 2000 mobile LINAC in treatments outside of the breast. After commissioning and external validation of dosimetry, we report in vivo results of measurements for treatments outside the breast in a large patient cohort, and investigate if the presence of inhomogeneities can affect in vivo measurements. METHODS AND MATERIALS: Applicator factors and profile curves were measured with a stereotactic diode. The applicators factors of the 6 cm flat and beveled applicators were also confirmed with radiochromic films, parallel-plate ion chamber and by an external audit performed with ThermoLuminescent Dosimeters (TLDs). The influence of bone on dose was investigated by using radiochromic films attached to an insert equivalent to cortical bone, immersed in the water phantom. In vivo dosimetry was performed on 126 patients treated with IOERT using metal oxide-silicon semiconductor field effect transistors (MOSFETs) placed on the tumor bed. RESULTS: Relatively small differences were found among different detectors for measurements of applicator factors. In the external audit, the agreement with the TLD was mostly within ±0.2%. The largest increase of dose due to the presence of cortical bone insert was +6.0% with energy 12 MeV and 3 cm applicator. On average, in vivo dose was significantly (+3.1%) larger than prescribed dose. CONCLUSION: IOERT in applications outside the breast results in low discrepancies between in vivo and prescribed doses, which can be also explained with the presence of tissue inhomogeneity.

Image-guided volumetric arc radiotherapy of pancreatic cancer with simultaneous integrated boost: Optimization strategies and dosimetric results.

PURPOSE: To introduce volumetric modulated arc therapy treatments (VMAT) with simultaneous integrated boost (SIB) for pancreatic cancer and describe dosimetric results on a large patient series. METHODS AND MATERIALS: 45 patients with pancreatic malignancies were treated with 18 MV single-arc VMAT. Image guidance was performed with daily online kilo-volt cone-beam computed tomography (CBCT). The conformity index (CI) and homogeneity index (HI) to the target volumes, PTV45Gy and PTV54Gy, and dose-volume indices to OARs from the QUANTEC task group were reported. The risk of clinical nephritis was evaluated using normal tissue complication probability (NTCP). Treatments were verified in-phantom with the Delta4 system. RESULTS: Average CI was 1.06 with 95% confidence intervals (95% CI) of 0.97-1.22 for PTV45Gy and 1.17 (0.66-1.61) for PTV54Gy. HI of PTV54Gy was 1.06 (1.04-1.10). OAR constraints were achieved in all patients, except for kidneys V12Gy of 48 (35.4-72.3)%. NTCP of the kidneys was 0.98 (0.6-1.7)%. Kidneys V12Gy and V20Gy were inversely related to PTV54Gy CI and maximum dose. All in-phantom tests had gamma pass rates exceeding 95% with global 3% dose difference and 3 mm distance to agreement. Patient shifts measured with CBCT had 95% CI of -0.8, +0.8 in the RL, -0.7, +0.8 in the SI, and -0.8, +0.7 cm in the AP directions. CONCLUSIONS: Dosimetric results of VMAT were excellent on PTVs and organs at risk. The kidneys represent the dose-limiting organ at risk for this technique. NTCP indicates that this technique is safe from radiation-induced side effects to the kidneys.

Dose to the skin in helical tomotherapy: results of in vivo measurements with radiochromic films.

PURPOSE: The aim of this study is to report results of measurements of dose to the skin in vivo with radiochromic EBT films in treatments with helical tomotherapy. METHODS AND MATERIALS: In vivo measurements were performed by applying pieces of radiochromic films to the skin or to the inner side of thermoplastic mask before the treatment. The sites of treatment included scalp, brain, head and neck, cranio-spinal axis and lower limbs. Skin dosimetry was performed in a patient who experienced grade 3-4 acute side effects to the skin shortly after the first treatment sessions. For each patient we measured the setup errors using the daily MVCT acquired for image guidance of the treatment. EBT films were read with a flatbed Epson Expression scanner and images were processed with an in-house written routine. RESULTS: A total of 96 measurements of dose to the skin performed on 14 patients. The mean difference and standard error of the mean difference between measured and TPS-calculated dose was -9.2% ± 2.6% for all treatments, -6.6% ± 2.6% for head and neck treatments. These differences were statistically significant at the 0.05 significance level (t-Student test). Planned dose and dose range in the region of measurements were not correlated with dose discrepancy. CONCLUSIONS: Radiochromic EBT films are suitable detectors for surface dose measurements in tomotherapy treatments. Results show that TPS overestimates dose to the skin measured with EBT radiochromic films. In vivo skin measurements with EBT films are a useful tool for quality assurance of tomotherapy treatments, as the treatment planning system may not give accurate dose values at the surface.

Helical tomotherapy in children and adolescents: dosimetric comparisons, opportunities and issues.

Helical Tomotherapy (HT) is a highly conformal image-guided radiation technique, introduced into clinical routine in 2006 at the Centro di Riferimento Oncologico Aviano (Italy). With this new technology, intensity-modulated radiotherapy (IMRT) is delivered using a helicoidal method. Here we present our dosimetric experiences using HT in 100 children, adolescents and young adults treated from May 2006 to February 2011. The median age of the patients was 13 years (range 1-24). The most common treated site was the central nervous system (50; of these, 24 were craniospinal irradiations), followed by thorax (22), head and neck (10), abdomen and pelvis (11), and limbs (7). The use of HT was calculated in accordance to the target dose conformation, the target size and shape, the dose to critical organs adjacent to the target, simultaneous treatment of multiple targets, and re-irradiation. HT has demonstrated to improve target volume dose homogeneity and the sparing of critical structures, when compared to 3D Linac-based radiotherapy (RT). In standard cases this technique represented a comparable alternative to IMRT delivered with conventional linear accelerator. In certain cases (e.g., craniospinal and pleural treatments) only HT generated adequate treatment plans with good target volume coverage. However, the gain in target conformality should be balanced with the spread of low-doses to distant areas. This remains an open issue for the potential risk of secondary malignancies (SMNs) and longer follow-up is mandatory.